What problem does it solve? Writing effective skills for AI agents is hard: descriptions fail to trigger, instructions bloat, and agents rush steps or ignore rules. This Skill supplies a shared vocabulary and a set of design principles that make a skill behave predictably on every run. ## Core Features & Use Cases - Invocation Design: Explains the trade-off between model-invoked skills (agent-discoverable, paying context load) and user-invoked skills (human-triggered, paying cognitive load), including router skills. - Information Hierarchy: Defines how to arrange steps and reference material across SKILL.md and disclosed files via progressive disclosure and context pointers. - Failure-Mode Diagnosis: Catalogs predictable failure modes — premature completion, duplication, sediment, sprawl, no-ops, and negation — with the specific lever that cures each. - Use Case: When editing a skill whose agent keeps skipping steps, consult the failure modes section to sharpen completion criteria or split the sequence to hide post-completion steps. ## Quick Start Ask the agent to review your SKILL.md using the writing-great-skills principles and suggest improvements to its description and structure.
